Why did we open-source our inference engine? Read the post

ibm-granite/granite-embedding-english-r2

Model Summary: Granite-embedding-english-r2 is a 149M parameter dense biencoder embedding model from the Granite Embeddings collection that can be used to generate high quality text embeddings.

Overview

Architecture
ModernBERT
Parameters
149M
Tasks
Encode
Outputs
Dense
Dimensions
Dense: 768
Max Sequence Length
8,192 tokens
License
apache-2.0
Languages
en

Benchmarks

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
map at 10 0.2887
mrr at 10 0.3356
ndcg at 10 0.3684
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
map at 10 0.3071
mrr at 10 0.4558
ndcg at 10 0.3856
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3450
map at 10 0.1295
mrr at 10 0.5521
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
map at 10 0.0507
mrr at 10 0.1451
ndcg at 10 0.0883
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
map at 10 0.7176
mrr at 10 0.7277
ndcg at 10 0.7634
Reference →

StackOverflowQA

technology retrieval en

Programming question answering from Stack Overflow

Corpus: 19,931 Queries: 1,994
Quality
map at 10 0.9016
mrr at 10 0.9016
ndcg at 10 0.9178
Reference →

Self-hosted inference for search & document processing

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.

Github 2.0K

Contact us

Tell us about your use case and we'll get back to you shortly.